Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    `.htmlurl`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ा
    0.80
    یت
    0.63
    ائی
    0.59
    یم
    0.57
    この
    0.57
    िट
    0.56
    かかる
    0.55
    antiate
    0.54
     ถ้า
    0.54
    ाइ
    0.54
    POSITIVE LOGITS
    이랑
    0.78
    al
    0.70
     in
    0.69
    ة
    0.65
     vores
    0.64
    6
    0.64
    Selon
    0.63
     jaren
    0.62
    wym
    0.61
     recher
    0.61
    Act Density 0.050%

    No Known Activations